Episodic Training for Domain Generalization

@article{Li2019EpisodicTF,
  title={Episodic Training for Domain Generalization},
  author={Da Li and J. Zhang and Yongxin Yang and Cong Liu and Yi-Zhe Song and Timothy M. Hospedales},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={1446-1455}
}
Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training domains. [...] Key Method Specifically, we decompose a deep network into feature extractor and classifier components, and then train each component by simulating it interacting with a partner who is badly tuned for the current domain.Expand
92 Citations
Batch Normalization Embeddings for Deep Domain Generalization
  • 3
  • PDF
Domain Adaptive Ensemble Learning
  • 5
  • PDF
Learning to Generate Novel Domains for Domain Generalization
  • 8
  • PDF
Robust Domain-Free Domain Generalization with Class-aware Alignment
  • 1
  • PDF
Latent Domain Learning with Dynamic Residual Adapters
  • 2
  • PDF
Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
  • 5
  • Highly Influenced
  • PDF
Domain Generalization via Model-Agnostic Learning of Semantic Features
  • 101
  • Highly Influenced
  • PDF
Learning to Generalize One Sample at a Time with Self-Supervision
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 57 REFERENCES
Best Sources Forward: Domain Generalization through Source-Specific Nets
  • 38
  • Highly Influential
  • PDF
Deeper, Broader and Artier Domain Generalization
  • 255
  • PDF
Learning to Generalize: Meta-Learning for Domain Generalization
  • 196
  • PDF
Domain-Adversarial Training of Neural Networks
  • 3,063
  • Highly Influential
  • PDF
Unsupervised Domain Adaptation by Backpropagation
  • 2,070
  • PDF
Domain Separation Networks
  • 713
  • PDF
Generalizing Across Domains via Cross-Gradient Training
  • 106
  • Highly Influential
  • PDF
...
1
2
3
4
5
...